qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[PATCH v2 18/20] target/mips: msa: Split helpers for MOD_<S|U>.<B|H|W|D>


From: Aleksandar Markovic
Subject: [PATCH v2 18/20] target/mips: msa: Split helpers for MOD_<S|U>.<B|H|W|D>
Date: Wed, 25 Sep 2019 14:46:10 +0200

From: Aleksandar Markovic <address@hidden>

Achieves clearer code and slightly better performance.

Signed-off-by: Aleksandar Markovic <address@hidden>
---
 target/mips/helper.h     |  12 +++-
 target/mips/msa_helper.c | 156 +++++++++++++++++++++++++++++++++++++++++------
 target/mips/translate.c  |  38 ++++++++++--
 3 files changed, 180 insertions(+), 26 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index ec4982f..cc216f7 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -877,6 +877,16 @@ DEF_HELPER_4(msa_div_u_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_div_u_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_div_u_d, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_mod_u_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_mod_u_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_mod_u_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_mod_u_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_mod_s_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_mod_s_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_mod_s_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_mod_s_d, void, env, i32, i32, i32)
+
 
 DEF_HELPER_4(msa_andi_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ori_b, void, env, i32, i32, i32)
@@ -939,8 +949,6 @@ DEF_HELPER_5(msa_asub_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_mulv_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_maddv_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_msubv_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_mod_s_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_mod_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_dotp_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_dotp_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_dpadd_s_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 5f64e51..8ad9d42 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -1715,7 +1715,144 @@ void helper_msa_div_u_d(CPUMIPSState *env, uint32_t wd, 
uint32_t ws, uint32_t wt
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Int Modulo group helpers here */
+static inline int64_t msa_mod_s_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    if (arg1 == DF_MIN_INT(df) && arg2 == -1) {
+        return 0;
+    }
+    return arg2 ? arg1 % arg2 : arg1;
+}
+
+void helper_msa_mod_s_b(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[1]);
+    pwd->b[2]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[2]);
+    pwd->b[3]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[3]);
+    pwd->b[4]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[4]);
+    pwd->b[5]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[5]);
+    pwd->b[6]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[6]);
+    pwd->b[7]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[7]);
+    pwd->b[8]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[8]);
+    pwd->b[9]  = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[9]);
+    pwd->b[10] = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[10]);
+    pwd->b[11] = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[11]);
+    pwd->b[12] = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[12]);
+    pwd->b[13] = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[13]);
+    pwd->b[14] = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[14]);
+    pwd->b[15] = msa_mod_s_df(DF_BYTE, pws->b[0],  pwt->b[15]);
+}
+
+void helper_msa_mod_s_h(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[1]);
+    pwd->h[2]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[2]);
+    pwd->h[3]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[3]);
+    pwd->h[4]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[4]);
+    pwd->h[5]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[5]);
+    pwd->h[6]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[6]);
+    pwd->h[7]  = msa_mod_s_df(DF_HALF, pws->h[0],  pwt->h[7]);
+}
+
+void helper_msa_mod_s_w(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_mod_s_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_mod_s_df(DF_WORD, pws->w[0],  pwt->w[1]);
+    pwd->w[2]  = msa_mod_s_df(DF_WORD, pws->w[0],  pwt->w[2]);
+    pwd->w[3]  = msa_mod_s_df(DF_WORD, pws->w[0],  pwt->w[3]);
+}
+
+void helper_msa_mod_s_d(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_mod_s_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_mod_s_df(DF_DOUBLE, pws->d[0],  pwt->d[1]);
+}
+
+static inline int64_t msa_mod_u_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    uint64_t u_arg2 = UNSIGNED(arg2, df);
+    return u_arg2 ? u_arg1 % u_arg2 : u_arg1;
+}
+
+void helper_msa_mod_u_b(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[1]);
+    pwd->b[2]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[2]);
+    pwd->b[3]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[3]);
+    pwd->b[4]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[4]);
+    pwd->b[5]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[5]);
+    pwd->b[6]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[6]);
+    pwd->b[7]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[7]);
+    pwd->b[8]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[8]);
+    pwd->b[9]  = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[9]);
+    pwd->b[10] = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[10]);
+    pwd->b[11] = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[11]);
+    pwd->b[12] = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[12]);
+    pwd->b[13] = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[13]);
+    pwd->b[14] = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[14]);
+    pwd->b[15] = msa_mod_u_df(DF_BYTE, pws->b[0],  pwt->b[15]);
+}
+
+void helper_msa_mod_u_h(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[1]);
+    pwd->h[2]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[2]);
+    pwd->h[3]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[3]);
+    pwd->h[4]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[4]);
+    pwd->h[5]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[5]);
+    pwd->h[6]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[6]);
+    pwd->h[7]  = msa_mod_u_df(DF_HALF, pws->h[0],  pwt->h[7]);
+}
+
+void helper_msa_mod_u_w(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_mod_u_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_mod_u_df(DF_WORD, pws->w[0],  pwt->w[1]);
+    pwd->w[2]  = msa_mod_u_df(DF_WORD, pws->w[0],  pwt->w[2]);
+    pwd->w[3]  = msa_mod_u_df(DF_WORD, pws->w[0],  pwt->w[3]);
+}
+
+void helper_msa_mod_u_d(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t 
wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_mod_u_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_mod_u_df(DF_DOUBLE, pws->d[0],  pwt->d[1]);
+}
 
 
 /*
@@ -2394,21 +2531,6 @@ static inline int64_t msa_mulv_df(uint32_t df, int64_t 
arg1, int64_t arg2)
     return arg1 * arg2;
 }
 
-static inline int64_t msa_mod_s_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    if (arg1 == DF_MIN_INT(df) && arg2 == -1) {
-        return 0;
-    }
-    return arg2 ? arg1 % arg2 : arg1;
-}
-
-static inline int64_t msa_mod_u_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t u_arg1 = UNSIGNED(arg1, df);
-    uint64_t u_arg2 = UNSIGNED(arg2, df);
-    return u_arg2 ? u_arg1 % u_arg2 : u_arg1;
-}
-
 #define SIGNED_EVEN(a, df) \
         ((((int64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
 
@@ -2614,8 +2736,6 @@ MSA_BINOP_DF(subsuu_s)
 MSA_BINOP_DF(asub_s)
 MSA_BINOP_DF(asub_u)
 MSA_BINOP_DF(mulv)
-MSA_BINOP_DF(mod_s)
-MSA_BINOP_DF(mod_u)
 MSA_BINOP_DF(dotp_s)
 MSA_BINOP_DF(dotp_u)
 MSA_BINOP_DF(srar)
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 27eca0a..5039716 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28642,6 +28642,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext 
*ctx)
             break;
         }
         break;
+    case OPC_MOD_S_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_mod_s_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_mod_s_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_mod_s_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_mod_s_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_MOD_U_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_mod_u_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_mod_u_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_mod_u_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_mod_u_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_SLL_df:
         gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28738,18 +28770,12 @@ static void gen_msa_3r(CPUMIPSState *env, 
DisasContext *ctx)
     case OPC_MAX_A_df:
         gen_helper_msa_max_a_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MOD_S_df:
-        gen_helper_msa_mod_s_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ILVEV_df:
         gen_helper_msa_ilvev_df(cpu_env, tdf, twd, tws, twt);
         break;
     case OPC_MIN_A_df:
         gen_helper_msa_min_a_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MOD_U_df:
-        gen_helper_msa_mod_u_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ILVOD_df:
         gen_helper_msa_ilvod_df(cpu_env, tdf, twd, tws, twt);
         break;
-- 
2.7.4




reply via email to

[Prev in Thread] Current Thread [Next in Thread]